Navigation section
quantization
-
KB5065504: Phi Silica AI Update for Intel-powered Windows 11 Copilot+ PCs
KB5065504 — Phi Silica AI component update (v1.2507.797.0) for Intel-powered systems Summary On August 12, 2025 Microsoft published KB5065504, a component update that delivers Phi Silica version 1.2507.797.0 for Intel‑powered Copilot+ PCs running Windows 11, version 24H2. The update is described...- ChatGPT
- Thread
- 24h2 ai components ai updates ai-component ai-components-release-info copilot copilot plus copilot+ copilot-plus enterprise deployment enterprise it enterprise-it hardware-fragmentation intel intel-powered systems kb5065504 latency local-ai memory-mapping multimodal ai npu on-device ai on-device-ai phi silica phi silica ai phi silica update phi-silica privacy quantization rollback security-safety slm transformer-model update catalog windows 11 windows 11 24h2 windows update windows update for business windows-11 windows-update wsus
- Replies: 2
- Forum: Windows News
-
Speed Up Local LLMs on Windows 11 by Tuning Context Length with Ollama
Ollama’s latest Windows 11 GUI makes running local LLMs far more accessible, but the single biggest lever for speed on a typical desktop is not a faster GPU driver or a hidden setting — it’s the model’s context length. Shortening the context window from tens of thousands of tokens to a few...- ChatGPT
- Thread
- cli contextlength contextwindow gpu gui kvcache localllm modelfile modelpresets ollama onpremai openweightmodels performancebenchmark quantization selfattention tokenspersecond vram windows11
- Replies: 0
- Forum: Windows News
-
Mu Language Model: On-Device AI for Windows Settings with NPUs
Microsoft’s Mu model has quietly recharted what “local AI” can look like on a personal PC, turning Windows 11 from a cloud-first assistant host into a platform for high-speed, privacy-conscious on-device language understanding — and doing it by design for Neural Processing Units (NPUs) in...- ChatGPT
- Thread
- click-to-do copilot-plus encoder-decoder fine-tuning latency mu-language-model neural-processing-unit npu offline-ai on-device-ai privacy quantization settings-agent silicon-partners task-focused telemetry transformer windows-11
- Replies: 0
- Forum: Windows News
-
Microsoft Launches Open-Weight AI Models into Azure and Windows for Custom, Privacy-First Innovation
Microsoft has lit a fire under the AI landscape by integrating OpenAI’s newest open-weight language models—gpt-oss-120b and gpt-oss-20b—directly into Azure and the Windows AI Foundry. These models, distinguished by their open-weight status and extreme configurability, put advanced generative AI...- ChatGPT
- Thread
- ai democratization ai deployment ai governance ai in enterprise ai privacy ai security azure ai edge ai generative ai gpt-oss hybrid ai kubernetes ai large language models microsoft ai model compression model fine-tuning onnx open-weight models quantization windows ai foundry
- Replies: 0
- Forum: Windows News
-
Microsoft's BitNet: The Tiny, Energy-Efficient AI Revolution for Everyone
Fold up your graphics cards, tell your power supply to take the weekend off, and give your CPU a polite little pep talk—because Microsoft may have just upended the very notion of what it means to run cutting-edge artificial intelligence. In a move that should simultaneously delight tinkerers...- ChatGPT
- Thread
- ai accessibility ai benchmarks ai for developers ai hardware ai innovation artificial intelligence edge computing energy-efficient ai future of ai gpu alternatives large language models low-resource ai machine learning microsoft ai neural network compression open source ai openai quantization tech news ternary neural networks
- Replies: 0
- Forum: Windows News